Brugada syndrome is a hereditary disease characterized by abnormal heart rhythm that is at high risk of ventricular arrhythmia and sudden cardiac death. In terms of ECG changes, Type 1 Brugada pattern is considered to be the most clinically relevant among all other types because it reflects the typical ECG pattern. It is important to accurately distinguish between this type of pattern, but it is not always easy since there are some minor waveform differences, sporadic nature, and similarity with other ECG changes. This thesis presents the design of an end to end pipeline that is intended forthe automatic detection of Brugada Syndrome Type 1 based on digitalization of electrocardiogram (ECG) signals via deep learning.